{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/dancing-in-the-dark-private-multi-party","title":"Dancing in the Dark: Private Multi-Party Machine Learning in an Untrusted Setting","arxiv_id":"1811.09712","date":"2018-11-23","proceeding":null,"authors":["Clement Fung","Jamie Koerner","Stewart Grant","Ivan Beschastnikh"],"abstract":"Distributed machine learning (ML) systems today use an unsophisticated threat\nmodel: data sources must trust a central ML process. We propose a brokered\nlearning abstraction that allows data sources to contribute towards a\nglobally-shared model with provable privacy guarantees in an untrusted setting.\nWe realize this abstraction by building on federated learning, the state of the\nart in multi-party ML, to construct TorMentor: an anonymous hidden service that\nsupports private multi-party ML.\n  We define a new threat model by characterizing, developing and evaluating new\nattacks in the brokered learning setting, along with new defenses for these\nattacks. We show that TorMentor effectively protects data providers against\nknown ML attacks while providing them with a tunable trade-off between model\naccuracy and privacy. We evaluate TorMentor with local and geo-distributed\ndeployments on Azure/Tor. In an experiment with 200 clients and 14 MB of data\nper client, our prototype trained a logistic regression model using stochastic\ngradient descent in 65s.\n  Code is available at: https://github.com/DistributedML/TorML","url_abs":"http://arxiv.org/abs/1811.09712v2","url_pdf":"http://arxiv.org/pdf/1811.09712v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"dancing-in-the-dark-private-multi-party","repo_url":"https://github.com/DistributedML/TorML","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":"machine-learning","task_name":"BIG-bench Machine Learning"},{"task_slug":"federated-learning","task_name":"Federated Learning"}],"methods":[{"method_slug":"logistic-regression","method_name":"Logistic Regression"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}